CN113821728B - Content Recommendation Method and Device - Google Patents

Content Recommendation Method and Device Download PDF

Info

Publication number
CN113821728B
CN113821728B CN202111155959.9A CN202111155959A CN113821728B CN 113821728 B CN113821728 B CN 113821728B CN 202111155959 A CN202111155959 A CN 202111155959A CN 113821728 B CN113821728 B CN 113821728B
Authority
CN
China
Prior art keywords
weight
content
screening rule
preset
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111155959.9A
Other languages
Chinese (zh)
Other versions
CN113821728A (en
Inventor
黄泽坚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202111155959.9A priority Critical patent/CN113821728B/en
Publication of CN113821728A publication Critical patent/CN113821728A/en
Application granted granted Critical
Publication of CN113821728B publication Critical patent/CN113821728B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9538—Presentation of query results
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/253—Fusion techniques of extracted features
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The application provides a content recommendation method and device. The method comprises the following steps: acquiring a plurality of contents to be recommended for recommending to a user, acquiring content information corresponding to each content to be recommended, and acquiring user information of the user; determining a content screening rule based on content information corresponding to the plurality of contents to be recommended, determining a relationship among the plurality of contents to be recommended based on the content information, determining a relationship screening rule based on the relationship among the plurality of contents to be recommended, and determining a user screening rule based on user information; fusing the content screening rules, the relation screening rules and the user screening rules to obtain target screening rules obtained by fusing a plurality of rules; based on a target screening rule, screening a plurality of contents to be recommended to obtain a set of contents to be displayed, and displaying the set of contents to be displayed so as to recommend the contents in the set of contents to be displayed.

Description

Content recommendation method and device
Technical Field
The present application relates to the field of computers and communications technologies, and in particular, to a content recommendation method and apparatus.
Background
To meet the needs of users, it is often necessary to recommend content to the user. In the prior art, the recommended content is generally based on the browsing record of the user, and the recommended content related to the browsing record is recommended, and when the browsing record of the user is less, the recommended result may be inaccurate.
Disclosure of Invention
The application aims to provide a content recommendation method and device, which can solve the problem of inaccurate recommendation results to a certain extent.
According to an aspect of an embodiment of the present application, there is provided a content recommendation method including: acquiring a plurality of contents to be recommended for recommending to a user, acquiring content information corresponding to each content to be recommended, and acquiring user information of the user; determining a content screening rule based on content information corresponding to a plurality of contents to be recommended, determining a relation among the plurality of contents to be recommended based on the plurality of content information, determining a relation screening rule based on the relation among the plurality of contents to be recommended, and determining a user screening rule based on the user information; fusing the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule; and screening the plurality of contents to be recommended based on the target screening rule to obtain a set of contents to be displayed, and displaying the set of contents to be displayed so as to recommend the contents in the set of contents to be displayed.
According to an aspect of an embodiment of the present application, there is provided a content recommendation apparatus including: the acquisition module is configured to acquire a plurality of contents to be recommended for recommending to a user, acquire content information corresponding to each content to be recommended, and acquire user information of the user; the determining module is configured to determine content screening rules based on content information corresponding to a plurality of to-be-recommended contents, determine relationships among the plurality of to-be-recommended contents based on the plurality of content information, determine relationship screening rules based on the relationships among the plurality of to-be-recommended contents, and determine user screening rules based on the user information; the fusion module is configured to fuse the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule; and the screening module is configured to screen a plurality of contents to be recommended based on the target screening rule to obtain a set of contents to be displayed and display the contents to be displayed.
In one embodiment of the present application, based on the foregoing scheme, the fusion module is configured to: screening the plurality of contents to be recommended based on the content screening rule to obtain a first recommendation group, screening the plurality of contents to be recommended based on the relation screening rule to obtain a second recommendation group, and screening the plurality of contents to be recommended based on the user screening rule to obtain a third recommendation group; taking the same content in the first recommendation group, the second recommendation group and the first recommendation group as standard content; determining a first preparation weight a2 corresponding to the content screening rule, a second preparation weight b2 corresponding to the relation screening rule and a third preparation weight c2 corresponding to the user screening rule based on the standard content; based on the first preliminary weight a2, the second preliminary weight b2, and the third preliminary weight c2, the content screening rule, the relationship screening rule, and the user screening rule are fused.
In one embodiment of the present application, based on the foregoing scheme, the fusion module is configured to: acquiring a first preset weight a1 preset by the content screening rule and a second preset weight a1 preset by the relation screening rule The second preset weight b1 and the third preset weight c1 preset by the user screening rule; substituting the first preset weight a1 and the first preliminary weight a2 into the formula y1=e (a1+a2) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1 and the second preliminary weight b2 into the formula y2=e (b1+b2) Obtaining a second weight y2 corresponding to the second recommendation group; substituting the third preset weight c1 and the third preliminary weight c2 into the formula y3=e (c1+c2) Obtaining a third weight y3 corresponding to the third recommendation group; and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
In one embodiment of the present application, based on the foregoing scheme, the fusion module is configured to: acquiring a first preset weight a1 preset by the content screening rule, a second preset weight b1 preset by the relation screening rule and a third preset weight c1 preset by the user screening rule; acquiring historical selection content of the user; acquiring the content of which the content in the first recommendation group is the same as the historically selected content, wherein the content accounts for the proportion of the first recommendation group and is used as a first historical coverage weight a3 corresponding to the content screening rule; acquiring the content of which the content in the second recommendation group is the same as the history selection content, wherein the content accounts for the proportion of the second recommendation group and is used as a second history coverage weight b3 corresponding to the relation screening rule; acquiring the content of which the content in the third recommendation group is the same as the historically selected content, wherein the content accounts for the proportion of the third recommendation group and is used as a third historical coverage weight c3 corresponding to the user screening rule; substituting the first preset weight a1, the first preliminary weight a2 and the first historical coverage weight a3 into the formula y1=e (a1+a2+a3) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2 and the second historical coverage weight b3 into the formula y2=e (b1+b2+b3) Obtaining a second weight y2 corresponding to the second recommendation group; the third preset weight c1, the third preliminary weight c2 and the third preliminary weight c2 are calculatedThe third historical coverage weight c3 is substituted into the formula y3=e (c1+c2+c3) Obtaining a third weight y3 corresponding to the third recommendation group; and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
In one embodiment of the present application, based on the foregoing scheme, the fusion module is configured to: acquiring a first preset weight a1 preset by the content screening rule, a second preset weight b1 preset by the relation screening rule and a third preset weight c1 preset by the user screening rule; acquiring historical selection content of the user; determining a first historical coverage weight a3 corresponding to the content screening rule, a second historical coverage weight b3 corresponding to the relation screening rule and a third historical coverage weight c3 corresponding to the user screening rule based on the historical selection content; the number of times that the content identical to the history selection content in the first recommendation group appears in the history selection content is used as a first history selection weight a4; the number of times of occurrence of the same content as the history selection content in the second recommendation group in the history selection content is used as the second history selection weight b4; the number of times of occurrence of the same content as the history selection content in the third recommendation group in the history selection content is used as the third history selection weight c4; substituting the first preset weight a1, the first preliminary weight a2, the first historical coverage weight a3 and the first historical selection weight a4 into a formula y1=e (a1+a2+a3+a4) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2, the second historical coverage weight b3 and the second historical selection weight b4 into a formula y2=e (b1+b2+b3+b4) Obtaining a second weight y2 corresponding to the second recommendation group; substituting the third preset weight c1, the third preliminary weight c2, the third historical coverage weight c3 and the third historical selection weight c4 into a formula y3=e (c1 +c2+c3+c4) Obtaining a third weight y3 corresponding to the third recommendation group; based on the first weightAnd y1, a second weight y2 and a third weight y3, and fusing the content screening rule, the relation screening rule and the user screening rule.
In one embodiment of the present application, based on the foregoing scheme, the fusion module is configured to: acquiring content characteristics of content information in a first recommendation group, and determining a first expression based on the content characteristics in the first recommendation group; acquiring content characteristics of content information in a second recommendation group, and determining a second expression based on the content characteristics in the second recommendation group; acquiring content characteristics of content information in a third recommendation group, and determining a third expression based on the content characteristics in the third recommendation group; taking the first weight y1 as the weight of the first expression, taking the second weight y2 as the weight of the second expression, and taking the third weight y3 as the weight of the third expression; and calculating the weighted sum of the first expression, the second expression and the third expression to obtain the target screening rule.
In one embodiment of the present application, based on the foregoing scheme, the screening module is configured to: determining the characteristics of the content to be recommended based on the content information to be recommended; if the content characteristics of the content to be recommended accord with the target screening rule, adding the content to be recommended into the content set to be displayed; if the number of the to-be-recommended contents conforming to the target screening rule is smaller than the preset to-be-recommended number, calculating the difference N between the preset to-be-recommended number and the number of the to-be-recommended contents conforming to the target screening rule; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n1=nxy1/(y1+y2+y3) to obtain the number N1 of the contents selected from the first recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n2=nxy2/(y1+y2+y3) to obtain the number N2 of contents selected from a second recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n3=nxy3/(y1+y2+y3) to obtain the number N3 of contents selected from a third recommendation group; and forming the content set to be displayed by using the content n1 selected from the first recommendation group, the content n2 selected from the second recommendation group and the content n3 selected from the third recommendation group.
In one embodiment of the present application, based on the foregoing, before fusing the content screening rules, the relationship screening rules, and the user screening rules, the determining module is configured to: determining a similarity matrix between the plurality of content information; clustering based on the similarity matrix; and determining the content screening rule based on the clustered content information.
In one embodiment of the present application, based on the foregoing scheme, the determining module is configured to: acquiring feature vectors in a feature matrix of the content information; substituting the feature vector into a formula:
obtaining a similarity vector Z, wherein X and Y respectively represent the feature vectors of corresponding positions in the feature matrix of any two pieces of content information, and e |X-Y| Represents a function based on a constant E and an index of |X-Y|, E (X-Y) represents the covariance of (X-Y), E -1 (X-Y) represents the inverse moment of the covariance of (X-Y); and combining the similarity vectors according to the positions of the characteristic feature vectors in the characteristic matrix to obtain the similarity matrix.
According to an aspect of an embodiment of the present application, there is provided a computer program storage medium storing computer program instructions which, when executed by a computer, cause the computer to perform the method of any one of the above.
According to an aspect of an embodiment of the present application, there is provided an electronic apparatus including: a processor; a memory having stored thereon computer readable instructions which, when executed by the processor, implement a method as claimed in any one of the preceding claims.
According to an aspect of embodiments of the present application, there is provided a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the methods provided in the various alternative embodiments described above.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
in the technical scheme provided by some embodiments of the present application, a plurality of contents to be recommended for recommending to a user are obtained, content information corresponding to each of the contents to be recommended is obtained, and user information of the user is obtained; determining a content screening rule based on content information corresponding to the plurality of contents to be recommended, determining a relation among the plurality of contents to be recommended based on the plurality of content information, determining a relation screening rule based on the relation among the plurality of contents to be recommended, and determining a user screening rule based on user information; fusing the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule; based on the target screening rule, screening a plurality of contents to be recommended to obtain a set of contents to be displayed, displaying the set of contents to be displayed, and recommending the contents in the set of contents to be displayed.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of an embodiment of the application may be applied;
FIG. 2 schematically illustrates a flow diagram of a content recommendation method according to one embodiment of the application;
FIG. 3 schematically illustrates a block diagram of a content recommendation device according to one embodiment of the application;
fig. 4 is a hardware diagram of an electronic device, according to an example embodiment.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
Fig. 1 shows a schematic diagram of an exemplary system architecture 100 to which the technical solution of an embodiment of the application may be applied.
As shown in fig. 1, a system architecture 100 may include a client 101, a network 102, and a server 103. Network 102 is the medium used to provide communication links between clients 101 and servers 103. The network 102 may include various connection types, such as wired communication links, wireless communication links, and the like, as the application is not limited in this regard.
It should be understood that the number of clients 101, networks 102, and servers 103 in fig. 1 is merely illustrative. There may be any number of clients 101, networks 102, and servers 103, as desired for implementation. For example, the server 103 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a content delivery network (Content Delivery Network, CDN), and basic cloud computing services such as big data and an artificial intelligence platform. The client 101 may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc.
In one embodiment of the present application, when the task execution time is reached, the server 103 obtains a plurality of contents to be recommended for recommending to the user, and obtains content information corresponding to each of the contents to be recommended, and obtains user information of the user; determining a content screening rule based on content information corresponding to the plurality of contents to be recommended, determining a relation among the plurality of contents to be recommended based on the plurality of content information, determining a relation screening rule based on the relation among the plurality of contents to be recommended, and determining a user screening rule based on user information; fusing the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule; based on the target screening rule, screening a plurality of contents to be recommended to obtain a set of contents to be displayed, displaying the set of contents to be displayed, and recommending the contents in the set of contents to be displayed.
It should be noted that, the content recommendation method provided in the embodiment of the present application is generally executed by the server 103, and accordingly, the content recommendation device is generally disposed in the server 103. However, in other embodiments of the present application, the client 101 may also have a similar function to the server 103, so as to perform the content recommendation method provided by the embodiments of the present application.
The implementation details of the technical scheme of the embodiment of the application are described in detail below:
fig. 2 schematically illustrates a flowchart of a content recommendation method according to an embodiment of the present application, and an execution subject of the content recommendation method may be a server, such as the server 103 illustrated in fig. 1.
Referring to fig. 2, the content recommendation method at least includes steps S210 to S240, and is described in detail as follows:
in step S210, a plurality of contents to be recommended for recommending to a user are acquired, content information corresponding to each of the contents to be recommended is acquired, and user information of the user is acquired.
In one embodiment of the present application, the content information corresponding to each content to be recommended may include a content type, a number of times the content is selected in the history, a content description, and the like, for example, may include description information about whether the content is a hot content.
In one embodiment of the application, the user information may include basic information such as a user name, an age, a occupation, and behavior information such as a user history purchase record.
In step S220, a content filtering rule is determined based on content information corresponding to the plurality of content to be recommended, a relationship between the plurality of content to be recommended is determined based on the content information, a relationship filtering rule is determined based on the relationship between the plurality of content to be recommended, and a user filtering rule is determined based on the user information.
In one embodiment of the present application, the content information corresponding to the content to be recommended may include description information about whether the recommended content is a hot content, and hot content in the plurality of content to be recommended may be acquired, and the content filtering rule is determined according to information other than the description information for describing whether the recommended content is the hot content in the content information corresponding to the content to be recommended corresponding to the hot content.
In one embodiment of the present application, a similarity matrix between a plurality of content information may be determined; clustering based on the similarity matrix; based on the clustered content information, a content screening rule is determined.
In one embodiment of the present application, the feature direction in the feature matrix of the content information may be obtained, and the feature vector is substituted into the formula: Obtaining a similarity vector Z, wherein X and Y respectively represent the feature vectors of corresponding positions in the feature matrix of any two pieces of content information, and e |X-Y| Represents a function based on a constant E and an index of |X-Y|, E (X-Y) represents the covariance of (X-Y), E -1 (X-Y) represents the inverse moment of the covariance of (X-Y); and combining the similarity vectors according to the positions of the characteristic feature vectors in the characteristic matrix to obtain a similarity matrix. When |X-Y| is greater than 1, then e |X-Y| Significantly increases with increasing index; when |X-Y| is less than 1, then e || The difference between the features with large difference can be amplified as the index increases slowly, so that the determination of the similar content information is more convenient.
In one embodiment of the present application, in determining the similarity matrix between the plurality of content information, the content of each content information may be compared first, only the similarity matrix containing the same content is determined, and the similarity value not containing the same content is recorded as 0, thereby reducing the calculation amount.
In one embodiment of the present application, in determining the similarity matrix of content information including the same content, the feature matrix of each content information including the same content may be determined first to calculate the similarity matrix between the feature matrices of each two content information.
In one embodiment of the present application, the relationship between the content to be recommended may include: the combination relationship, the rejection relationship, the similarity relationship, and the like, for example, whether the contents to be recommended have the combination relationship, the rejection relationship, or the similarity relationship can be determined according to the function description in the content information.
In one embodiment of the application, the relationship screening rules may be set to: the contents of the mutual combination relation are in accordance with or not in accordance with the relation screening rule, the contents of the mutual exclusion relation can only have one in accordance with the relation screening rule, and the contents of the mutual similarity relation can only have one in accordance with the relation screening rule.
In one embodiment of the application, the user information may include customer base attribute information and customer history selection information.
In one embodiment of the present application, before determining the user filtering rule, a similarity matrix between the plurality of user information may be determined, clustering is performed based on the similarity matrix between the plurality of user information, and the content filtering rule is determined based on the clustered user information.
In one embodiment of the present application, the process of determining the similarity matrix between the plurality of user information may refer to the process of determining the similarity matrix between the individual content information.
With continued reference to fig. 2, in step S230, the content screening rule, the relationship screening rule, and the user screening rule are fused to obtain a target screening rule.
In one embodiment of the application, a first weight corresponding to the content screening rule can be determined, a second weight corresponding to the relation capacity screening rule can be determined, a third weight corresponding to the user screening rule can be determined, and the content screening rule, the relation screening rule and the user screening rule are fused based on the first weight, the second weight and the third weight to obtain the target screening rule.
In one embodiment of the present application, a first preset weight a1 may be preset for the content screening rule, a second preset weight b1 may be preset for the relationship screening rule, and a third preset weight c1 may be preset for the user screening rule.
In one embodiment of the present application, a plurality of contents to be recommended may be screened based on a content screening rule, to obtain a first recommendation group composed of contents to be recommended that conform to the content screening rule; screening the plurality of contents to be recommended based on the relation screening rule to obtain a second recommendation group consisting of the contents to be recommended conforming to the relation screening rule; and screening the plurality of contents to be recommended based on the user screening rule to obtain a third recommendation group consisting of the contents to be recommended which accord with the user screening rule.
In one embodiment of the present application, the same content in the first recommendation group, the second recommendation group, and the first recommendation group may be determined as standard content, and based on the standard content, a first preliminary weight a2 corresponding to the content screening rule, a second preliminary weight b2 corresponding to the relationship screening rule, and a third preliminary weight c2 corresponding to the user screening rule may be determined.
In one embodiment of the present application, the proportion of the standard content in the first recommendation group may be determined as the first preliminary weight a2 of the content screening rule, the proportion of the standard content in the second recommendation group may be determined as the second preliminary weight b2 of the relationship screening rule, and the proportion of the standard content in the third recommendation group may be determined as the third preliminary weight c2 of the user screening rule.
In one embodiment of the present application, the first preset weight a1 and the first preliminary weight a2 may be substituted into the formula y1=e (a1+a2) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1 and the second preliminary weight b2 into the formula y2=e (b1+b2) Obtaining a second weight y2 corresponding to a second recommendation group; the third preset weight c1 and the third preset weightSubstitution of the standby weight c2 into the formula y3=e (c1+c2) And obtaining a third weight y3 corresponding to the third recommendation group.
In one embodiment of the present application, history selection content of a user may be obtained, and based on the history selection content, a first history coverage weight a3 corresponding to a content screening rule, a second history coverage weight b3 corresponding to a relationship screening rule, and a third history coverage weight c3 corresponding to the user screening rule are determined.
In one embodiment of the present application, the ratio of the content identical to the history selection content in the first recommendation group to the first recommendation group may be used as the first history coverage weight a3; taking the proportion of the content which is the same as the history selection content in the second recommendation group and occupies the second recommendation group as a second history coverage weight b3; and taking the proportion of the content which is the same as the history selection content in the third recommendation group to the third recommendation group as a third history coverage weight c3.
In one embodiment of the present application, the first preset weight a1, the first preliminary weight a2, and the first historical coverage weight a3 may be substituted into the formula y1=e (a1+a2+a3) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2 and the second historical coverage weight b3 into the formula y2=e (b1+b2+b3) Obtaining a second weight y2 corresponding to a second recommendation group; substituting the third preset weight c1, the third preliminary weight c2 and the third historical coverage weight c3 into the formula y3=e (c1+c2+c3) And obtaining a third weight y3 corresponding to the third recommendation group.
In one embodiment of the present application, the number of occurrences of the same content as the history selection content in the first recommendation group in the history selection content may be taken as the first history selection weight a4; the number of times of occurrence of the same content as the history selection content in the second recommendation group in the history selection content is used as a second history selection weight b4; the number of times that the same content as the history selection content in the third recommendation group appears in the history selection content is taken as a third history selection weight c4.
In one embodiment of the present application, the first preset weight a1, the first preliminary weight a2, the first historical coverage weighta3 and the first historic selection weight a4 are substituted into the formula y1=e (a1+a2+a3+a4) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2, the second historical coverage weight b3 and the second historical selection weight b4 into the formula y2=e (b1+b2+b3+b4) Obtaining a second weight y2 corresponding to a second recommendation group; substituting the third preset weight c1, the third preliminary weight c2, the third historical coverage weight c3 and the third historical selection weight c4 into the formula y3=e (c1+c2+c3+c4) And obtaining a third weight y3 corresponding to the third recommendation group.
In one embodiment of the present application, a first expression of a content screening rule, a second expression of a relationship screening rule, and a third expression of a user screening rule may be determined, and the first expression, the second expression, and the third expression may be weighted and summed to obtain a target screening rule.
In one embodiment of the present application, content characteristics in a first recommendation group may be obtained, and a first expression is determined based on the content characteristics in the first recommendation group; content characteristics in the second recommendation group may be obtained, and a second expression is determined based on the content characteristics in the second recommendation group; content characteristics in the third recommendation group may be obtained, and a third expression may be determined based on the content characteristics in the third recommendation group.
In one embodiment of the present application, a first vector corresponding to each content in the first recommendation group may be used as each content feature in the first recommendation group; the second vector corresponding to each content in the second recommendation group can be used as each content characteristic in the second recommendation group; a third vector corresponding to each content in the third recommendation group may be used as each content feature in the third recommendation group.
In one embodiment of the present application, a first feature function that each first vector in the first recommendation set satisfies may be calculated based on each first vector in the first recommendation set as the first expression; a second characteristic function which is satisfied by each second vector in the second recommendation group can be calculated based on each second vector in the second recommendation group and used as a second expression; and calculating a third characteristic function which is met by the third vector of each content in the third recommendation group based on each third vector in the third recommendation group, and taking the third characteristic function as a third expression.
With continued reference to fig. 2, in step S240, a plurality of contents to be recommended are filtered based on the target filtering rule, so as to obtain a set of contents to be displayed, and the set of contents to be displayed is displayed, so as to recommend contents in the set of contents to be displayed.
In one embodiment of the application, each content feature corresponding to the content to be recommended is substituted into a target screening rule formed by the first expression, the second expression and the third expression respectively, and if the content feature corresponding to a certain content to be recommended accords with the target screening rule, the content to be recommended can be determined, so that the target screening rule is met; if the content characteristics corresponding to a certain content to be recommended do not meet the target screening rule, it can be determined that the content to be recommended does not meet the target screening rule.
In one embodiment of the application, if the content characteristics of the content to be recommended meet the target screening rule, adding the content to be recommended into the content set to be displayed; if the number of the to-be-recommended contents conforming to the target screening rule is smaller than the preset to-be-recommended number, calculating the difference N between the preset to-be-recommended number and the number of the to-be-recommended contents conforming to the target screening rule; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n1=nxy1/(y1+y2+y3) to obtain the number N1 of the contents selected from the first recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n2=nxy2/(y1+y2+y3) to obtain the number N2 of the contents selected from the second recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n3=nxy3/(y1+y2+y3) to obtain the number N3 of the contents selected from the third recommendation group; and combining the n1 content selected from the first recommendation group, the n2 content selected from the second recommendation group and the n3 content selected from the third recommendation group into a content set to be displayed.
In one embodiment of the present application, the content in the content set to be displayed may be displayed after being sequenced, so as to recommend the content in the content set to be displayed.
In one embodiment of the present application, profile information of each content to be displayed may be determined when the content to be displayed is ranked, and a matching relationship between the profile information and user information is calculated to determine the ranking.
In one embodiment of the present application, when determining profile information of each content to be displayed, element characteristics of each element of the content to be displayed may be obtained, similarity between every two elements is calculated, and the profile information of the content to be displayed is determined based on the element having similarity greater than the set similarity between the two elements, so as to avoid duplication.
In one embodiment of the application, the elemental signature may include display features such as elemental format, display location, color, pattern, etc.; the element features may also include intent features that may be input into a machine learning model to determine the intent features of the element.
In one embodiment of the present application, after the actual feedback is obtained by the presentation, each weight may be modified based on the feedback obtained by the presentation, and specifically, each weight may be modified by obtaining content information corresponding to the actual feedback whose estimated feedback differs by more than a set difference.
In the embodiment of fig. 2, by acquiring a plurality of contents to be recommended for recommending to a user, and acquiring content information corresponding to each of the contents to be recommended, and acquiring user information of the user; determining a content screening rule based on content information corresponding to the plurality of contents to be recommended, determining a relationship among the plurality of contents to be recommended based on the content information, determining a relationship screening rule based on the relationship among the plurality of contents to be recommended, and determining a user screening rule based on user information; fusing the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule; based on the target screening rule, screening a plurality of contents to be recommended to obtain a set of contents to be displayed, displaying the set of contents to be displayed, and recommending the contents in the set of contents to be displayed.
The following describes an embodiment of the apparatus of the present application, which may be used to perform the content recommendation method in the above embodiment of the present application. For details not disclosed in the embodiments of the apparatus of the present application, please refer to the embodiments of the content recommendation method of the present application.
Fig. 3 schematically shows a block diagram of a content recommendation device according to an embodiment of the application.
Referring to fig. 3, a content recommendation apparatus 300 according to an embodiment of the present application includes an acquisition module 301, a determination module 302, a fusion module 303, and a filtering module 304.
According to an aspect of the embodiment of the present application, based on the foregoing solution, the obtaining module 301 is configured to obtain a plurality of to-be-recommended contents, and obtain content information corresponding to each to-be-recommended content, and obtain user information; the determining module 302 is configured to determine a content screening rule based on content information corresponding to the plurality of content to be recommended, determine a relationship between the plurality of content to be recommended based on the plurality of content information, determine a relationship screening rule based on the relationship between the plurality of content to be recommended, and determine a user screening rule based on the user information; the fusion module 303 is configured to fuse the content screening rule, the relationship screening rule and the user screening rule to obtain a target screening rule; the filtering module 304 is configured to filter the plurality of contents to be recommended based on the target filtering rule, obtain a set of contents to be displayed, and display the contents to be displayed.
In one embodiment of the present application, based on the foregoing scheme, the fusion module 303 is configured to: screening the plurality of contents to be recommended based on a content screening rule to obtain a first recommendation group, screening the plurality of contents to be recommended based on a relation screening rule to obtain a second recommendation group, and screening the plurality of contents to be recommended based on a user screening rule to obtain a third recommendation group; taking the same content in the first recommendation group, the second recommendation group and the first recommendation group as standard content; determining a first preparation weight a2 corresponding to the content screening rule, a second preparation weight b2 corresponding to the relation screening rule and a third preparation weight c2 corresponding to the user screening rule based on standard content; the content screening rule, the relationship screening rule, and the user screening rule are fused based on the first preliminary weight a2, the second preliminary weight b2, and the third preliminary weight c 2.
In one embodiment of the present application, based on the foregoing scheme, the fusion module 303 is configured to: acquiring a first preset weight a1 preset by a content screening rule, a second preset weight b1 preset by a relation screening rule and a third preset weight c1 preset by a user screening rule; substituting the first preset weight a1 and the first preliminary weight a2 into the formula y1=e (a1+a2) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1 and the second preliminary weight b2 into the formula y2=e (b1+b2) Obtaining a second weight y2 corresponding to a second recommendation group; substituting the third preset weight c1 and the third preliminary weight c2 into a formula y3=e (c1+c2) to obtain a third weight y3 corresponding to a third recommendation group; and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
In one embodiment of the present application, based on the foregoing scheme, the fusion module 303 is configured to: acquiring a first preset weight a1 preset by a content screening rule, a second preset weight b1 preset by a relation screening rule and a third preset weight c1 preset by a user screening rule; acquiring historical selection content of a user; acquiring the content, which is the same as the history selection content, in the first recommendation group, and takes the content as the proportion of the first recommendation group as a first history coverage weight a3 corresponding to the content screening rule; acquiring the content, which is the same as the history selection content, in the second recommendation group, and takes the content as the proportion of the second recommendation group as a second history coverage weight b3 corresponding to the relation screening rule; acquiring the content of the third recommendation group, which is the same as the historically selected content and occupies the proportion of the third recommendation group, as the corresponding user screening rule A third historical coverage weight c3; substituting the first preset weight a1, the first preliminary weight a2 and the first historical coverage weight a3 into the formula y1=e (a1+a2+a3) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2 and the second historical coverage weight b3 into the formula y2=e (b1+b2+b3) Obtaining a second weight y2 corresponding to a second recommendation group; substituting the third preset weight c1, the third preliminary weight c2 and the third historical coverage weight c3 into the formula y3=e (c1+c2++c) Obtaining a third weight y3 corresponding to a third recommendation group; and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
In one embodiment of the present application, based on the foregoing scheme, the fusion module 303 is configured to: acquiring a first preset weight a1 preset by a content screening rule, a second preset weight b1 preset by a relation screening rule and a third preset weight c1 preset by a user screening rule; acquiring historical selection content of a user; determining a first historical coverage weight a3 corresponding to the content screening rule, a second historical coverage weight b3 corresponding to the relation screening rule and a third historical coverage weight c3 corresponding to the user screening rule based on the historical selection content; the number of times that the content identical to the history selection content in the first recommendation group appears in the history selection content is used as a first history selection weight a4; the number of times of occurrence of the same content as the history selection content in the second recommendation group in the history selection content is used as a second history selection weight b4; the number of times that the content identical to the history selection content in the third recommendation group appears in the history selection content is used as a third history selection weight c4; substituting the first preset weight a1, the first preliminary weight a2, the first historical coverage weight a3 and the first historical selection weight a4 into the formula y1=e (a1+a2+a3+a4) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2, the second historical coverage weight b3 and the second historical selection weight b4 into the formula y2=e (b1+b2+b3+b4) Obtaining a second weight y2 corresponding to a second recommendation group; covering the third preset weight c1, the third preliminary weight c2 and the third historySubstituting the weight c3 and the third historically selected weight c4 into the formula y3=e (c1+c2+c3+c4) Obtaining a third weight y3 corresponding to a third recommendation group; and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
In one embodiment of the present application, based on the foregoing scheme, the fusion module 303 is configured to: acquiring content characteristics of content information in a first recommendation group, and determining a first expression based on the content characteristics in the first recommendation group; acquiring content characteristics of content information in a second recommendation group, and determining a second expression based on the content characteristics in the second recommendation group; acquiring content characteristics of content information in a third recommendation group, and determining a third expression based on the content characteristics in the third recommendation group; taking the first weight y1 as the weight of the first expression, taking the second weight y2 as the weight of the second expression, and taking the third weight y3 as the weight of the third expression; and calculating the weighted sum of the first expression, the second expression and the third expression to obtain the target screening rule.
In one embodiment of the present application, based on the foregoing scheme, the screening module 304 is configured to: determining the characteristics of each content to be recommended based on the content information to be recommended; if the content characteristics of the content to be recommended accord with the target screening rule, adding the content to be recommended into the content set to be displayed; if the number of the to-be-recommended contents conforming to the target screening rule is smaller than the preset to-be-recommended number, calculating the difference N between the preset to-be-recommended number and the number of the to-be-recommended contents conforming to the target screening rule; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n1=nxy1/(y1+y2+y3) to obtain the number N1 of the contents selected from the first recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n2=nxy2/(y1+y2+y3) to obtain the number N2 of the contents selected from the second recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n3=nxy3/(y1+y2+y3) to obtain the number N3 of the contents selected from the third recommendation group; and combining the n1 content selected from the first recommendation group, the n2 content selected from the second recommendation group and the n3 content selected from the third recommendation group into a content set to be displayed.
In one embodiment of the present application, based on the foregoing, prior to fusing the content screening rules, the relationship screening rules, and the user screening rules, the determination module 302 is configured to: determining a similarity matrix between the plurality of content information; clustering based on the similarity matrix; based on the clustered content information, a content screening rule is determined.
In one embodiment of the present application, based on the foregoing scheme, the determining module 302 is configured to: acquiring feature vectors in a feature matrix of the content information; substituting the feature vector into the formula:
obtaining a similarity vector Z, wherein X and Y respectively represent the feature vectors of corresponding positions in the feature matrix of any two pieces of content information, and e |X-Y| Represents a function based on a constant E and an index of |X-Y|, E (X-Y) represents the covariance of (X-Y), E -1 (X-Y) represents the inverse moment of the covariance of (X-Y); and combining the similarity vectors according to the positions of the characteristic feature vectors in the characteristic matrix to obtain a similarity matrix.
Those skilled in the art will appreciate that the various aspects of the application may be implemented as a system, method, or program product. Accordingly, aspects of the application may be embodied in the following forms, namely: an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects may be referred to herein as a "circuit," module "or" system.
An electronic device 400 according to such an embodiment of the application is described below with reference to fig. 4. The electronic device 400 shown in fig. 4 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present application.
As shown in fig. 4, the electronic device 400 is embodied in the form of a general purpose computing device. The components of electronic device 400 may include, but are not limited to: the at least one processing unit 410, the at least one memory unit 420, a bus 430 connecting the different system components (including the memory unit 420 and the processing unit 410), and a display unit 440.
Wherein the storage unit stores program code that is executable by the processing unit 410 such that the processing unit 410 performs steps according to various exemplary embodiments of the present application described in the above-described "example methods" section of the present specification.
The storage unit 420 may include readable media in the form of volatile storage units, such as Random Access Memory (RAM) 421 and/or cache memory 422, and may further include Read Only Memory (ROM) 423.
The storage unit 420 may also include a program/utility 424 having a set (at least one) of program modules 425, such program modules 425 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 430 may be a local bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or using any of a variety of bus architectures.
The electronic device 400 may also communicate with one or more external devices (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 400, and/or with any device (e.g., router, modem, etc.) that enables the electronic device 400 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 450. Also, electronic device 400 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 over the bus 430. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 400, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a terminal device, or a network device, etc.) to perform the method according to the embodiments of the present application.
According to an embodiment of the present application, there is also provided a computer-readable storage medium having stored thereon a program product capable of implementing the method described above in the present specification. In some possible embodiments, the various aspects of the application may also be implemented in the form of a program product comprising program code for causing a terminal device to carry out the steps according to the various exemplary embodiments of the application as described in the "exemplary methods" section of this specification, when said program product is run on the terminal device.
According to one embodiment of the application, the program product for implementing the above method may employ a portable compact disc read-only memory (CD-ROM) and comprise program code and may be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto, and in this document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable signal medium may include a data signal propagated in baseband or as part of a carrier wave with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable signal medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
Furthermore, the above-described drawings are only schematic illustrations of processes included in the method according to the exemplary embodiment of the present application, and are not intended to be limiting. It will be readily appreciated that the processes shown in the above figures do not indicate or limit the temporal order of these processes. In addition, it is also readily understood that these processes may be performed synchronously or asynchronously, for example, among a plurality of modules.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (8)

1. A content recommendation method, comprising:
acquiring a plurality of contents to be recommended for recommending to a user, acquiring content information corresponding to each content to be recommended, and acquiring user information of the user;
determining a content screening rule based on content information corresponding to a plurality of contents to be recommended, determining a relation among the plurality of contents to be recommended based on the content information, determining a relation screening rule based on the relation among the plurality of contents to be recommended, and determining a user screening rule based on the user information;
Screening the plurality of contents to be recommended based on the content screening rule to obtain a first recommendation group, screening the plurality of contents to be recommended based on the relation screening rule to obtain a second recommendation group, and screening the plurality of contents to be recommended based on the user screening rule to obtain a third recommendation group;
taking the same content in the first recommendation group, the second recommendation group and the third recommendation group as standard content;
determining a first preparation weight a2 corresponding to the content screening rule, a second preparation weight b2 corresponding to the relation screening rule and a third preparation weight c2 corresponding to the user screening rule based on the standard content;
based on the first preliminary weight a2, the second preliminary weight b2 and the third preliminary weight c2, fusing the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule;
screening the plurality of to-be-recommended contents based on the target screening rule to obtain a to-be-displayed content set, and displaying the to-be-displayed content set to recommend contents in the to-be-displayed content set;
Wherein the fusing the content filtering rule, the relationship filtering rule, and the user filtering rule based on the first preliminary weight a2, the second preliminary weight b2, and the third preliminary weight c2 includes:
acquiring a first preset weight a1 preset by the content screening rule, a second preset weight b1 preset by the relation screening rule and a third preset weight c1 preset by the user screening rule;
substituting the first preset weight a1 and the first preliminary weight a2 into the formula y1=e (a1+a2) Obtaining a first weight y1 corresponding to the first recommendation group;
substituting the second preset weight b1 and the second preliminary weight b2 into the formula y2=e (b1+b2) Obtaining a second weight y2 corresponding to the second recommendation group;
substituting the third preset weight c1 and the third preliminary weight c2 into the formula y3=e (c1+c2) Obtaining a third weight y3 corresponding to the third recommendation group;
and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
2. The content recommendation method according to claim 1, wherein the fusing of the content screening rule, the relationship screening rule, and the user screening rule based on the first preliminary weight a2, the second preliminary weight b2, and the third preliminary weight c2 includes:
Acquiring a first preset weight a1 preset by the content screening rule, a second preset weight b1 preset by the relation screening rule and a third preset weight c1 preset by the user screening rule;
acquiring historical selection content of the user;
acquiring the content of which the content in the first recommendation group is the same as the historically selected content, wherein the content accounts for the proportion of the first recommendation group and is used as a first historical coverage weight a3 corresponding to the content screening rule;
acquiring the content of which the content in the second recommendation group is the same as the history selection content, wherein the content accounts for the proportion of the second recommendation group and is used as a second history coverage weight b3 corresponding to the relation screening rule;
acquiring the content of which the content in the third recommendation group is the same as the historically selected content, wherein the content accounts for the proportion of the third recommendation group and is used as a third historical coverage weight c3 corresponding to the user screening rule;
substituting the first preset weight a1, the first preliminary weight a2 and the first historical coverage weight a3 into the formula y1=e (a1+a2+a3) Obtaining a first weight y1 corresponding to the first recommendation group;
substituting the second preset weight b1, the second preliminary weight b2 and the second historical coverage weight b3 into the formula y2=e (b1+b2+b3) Obtaining a second weight y2 corresponding to the second recommendation group;
substituting the third preset weight c1, the third preliminary weight c2 and the third historical coverage weight c3 into the formula y3=e (c1+c2+c3) Obtaining a third weight y3 corresponding to the third recommendation group;
and fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
3. The content recommendation method according to claim 1, wherein the fusing of the content screening rule, the relationship screening rule, and the user screening rule based on the first preliminary weight a2, the second preliminary weight b2, and the third preliminary weight c2 includes:
acquiring a first preset weight a1 preset by the content screening rule, a second preset weight b1 preset by the relation screening rule and a third preset weight c1 preset by the user screening rule;
acquiring historical selection content of the user;
determining a first historical coverage weight a3 corresponding to the content screening rule, a second historical coverage weight b3 corresponding to the relation screening rule and a third historical coverage weight c3 corresponding to the user screening rule based on the historical selection content;
The number of times that the content identical to the history selection content in the first recommendation group appears in the history selection content is used as a first history selection weight a4; the number of times of occurrence of the same content in the second recommendation group as the history selection content is used as a second history selection weight b4; the number of times of occurrence of the same content in the third recommendation group as the history selection content is used as a third history selection weight c4;
substituting the first preset weight a1, the first preliminary weight a2, the first historical coverage weight a3 and the first historical selection weight a4 into a formula y1=e (a1+a2+a3+a4) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1, the second preliminary weight b2, the second historical coverage weight b3 and the second historical selection weight b4 into a formula y2=e (b1+b2+b3+b4) Obtaining a second weight y2 corresponding to the second recommendation group; substituting the third preset weight c1, the third preliminary weight c2, the third historical coverage weight c3 and the third historical selection weight c4 into a formula y3=e (c1+c2+c3+c4) Obtaining a third weight y3 corresponding to the third recommendation group;
And fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y 3.
4. A content recommendation method as claimed in claim 1, 2 or 3, wherein said fusing said content screening rules, said relationship screening rules and said user screening rules based on said first weight y1, second weight y2 and third weight y3 comprises:
acquiring content characteristics of content information in a first recommendation group, and determining a first expression based on the content characteristics in the first recommendation group;
acquiring content characteristics of content information in a second recommendation group, and determining a second expression based on the content characteristics in the second recommendation group;
acquiring content characteristics of content information in a third recommendation group, and determining a third expression based on the content characteristics in the third recommendation group;
taking the first weight y1 as the weight of the first expression, taking the second weight y2 as the weight of the second expression, and taking the third weight y3 as the weight of the third expression;
and calculating the weighted sum of the first expression, the second expression and the third expression to obtain the target screening rule.
5. The content recommendation method according to claim 4, wherein the screening the plurality of content to be recommended based on the target screening rule to obtain a set of content to be displayed includes:
determining the characteristics of the content to be recommended based on the content information to be recommended;
if the content characteristics of the content to be recommended accord with the target screening rule, adding the content to be recommended into the content set to be displayed;
if the number of the to-be-recommended contents conforming to the target screening rule is smaller than the preset to-be-recommended number, calculating the difference N between the preset to-be-recommended number and the number of the to-be-recommended contents conforming to the target screening rule;
substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n1=nxy1/(y1+y2+y3) to obtain the number N1 of the contents selected from the first recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n2=nxy2/(y1+y2+y3) to obtain the number N2 of contents selected from a second recommendation group; substituting the first weight y1, the second weight y2 and the third weight y3 into a formula n3=nxy3/(y1+y2+y3) to obtain the number N3 of contents selected from a third recommendation group;
And forming the content set to be displayed by using the content n1 selected from the first recommendation group, the content n2 selected from the second recommendation group and the content n3 selected from the third recommendation group.
6. The content recommendation method according to claim 1, wherein before screening the plurality of content to be recommended based on the content screening rule to obtain a first recommendation group, the method comprises:
determining a similarity matrix between the plurality of content information;
clustering based on the similarity matrix;
and determining the content screening rule based on the clustered content information.
7. The content recommendation method according to claim 6, wherein the determining a similarity matrix between a plurality of content information comprises:
acquiring feature vectors in a feature matrix of the content information;
substituting the feature vector into a formula:
obtaining a similarity vector Z, wherein X and Y respectively represent the feature vectors of corresponding positions in the feature matrix of any two pieces of content information, and e |X-Y| E (X-Y) represents the covariance of (X-Y), E -1 (X-Y) represents the inverse moment of the covariance of (X-Y);
and combining the similarity vectors according to the positions of the feature vectors in the feature matrix to obtain the similarity matrix.
8. A content recommendation device, comprising:
the acquisition module is configured to acquire a plurality of contents to be recommended for recommending to a user, acquire content information corresponding to each content to be recommended, and acquire user information of the user;
the determining module is configured to determine content screening rules based on content information corresponding to a plurality of to-be-recommended contents, determine relationships among the plurality of to-be-recommended contents based on the content information, determine relationship screening rules based on the relationships among the plurality of to-be-recommended contents, and determine user screening rules based on the user information;
the fusion module is configured to screen the plurality of contents to be recommended based on the content screening rule to obtain a first recommendation group, screen the plurality of contents to be recommended based on the relation screening rule to obtain a second recommendation group, and screen the plurality of contents to be recommended based on the user screening rule to obtain a third recommendation group; taking the same content in the first recommendation group, the second recommendation group and the third recommendation group as standard content; determining a first preparation weight a2 corresponding to the content screening rule, a second preparation weight b2 corresponding to the relation screening rule and a third preparation weight c2 corresponding to the user screening rule based on the standard content; based on the first preliminary weight a2, the second preliminary weight b2 and the third preliminary weight c2, fusing the content screening rule, the relation screening rule and the user screening rule to obtain a target screening rule; wherein the fusing the content filtering rule, the relationship filtering rule, and the user filtering rule based on the first preliminary weight a2, the second preliminary weight b2, and the third preliminary weight c2 includes: Acquiring a first preset weight a1 preset by the content screening rule, a second preset weight b1 preset by the relation screening rule and a third preset weight c1 preset by the user screening rule; substituting the first preset weight a1 and the first preliminary weight a2 into the formula y1=e (a1+a2) Obtaining a first weight y1 corresponding to the first recommendation group; substituting the second preset weight b1 and the second preliminary weight b2 into the formula y2=e (b1+b2) Obtaining a second weight y2 corresponding to the second recommendation group; substituting the third preset weight c1 and the third preliminary weight c2 into the formula y3=e (c1+c2) Obtaining a third weight y3 corresponding to the third recommendation group; fusing the content screening rule, the relation screening rule and the user screening rule based on the first weight y1, the second weight y2 and the third weight y3;
and the screening module is configured to screen a plurality of contents to be recommended based on the target screening rule to obtain a set of contents to be displayed and display the contents to be displayed.
CN202111155959.9A 2021-09-29 2021-09-29 Content Recommendation Method and Device Active CN113821728B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111155959.9A CN113821728B (en) 2021-09-29 2021-09-29 Content Recommendation Method and Device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111155959.9A CN113821728B (en) 2021-09-29 2021-09-29 Content Recommendation Method and Device

Publications (2)

Publication Number Publication Date
CN113821728A CN113821728A (en) 2021-12-21
CN113821728B true CN113821728B (en) 2023-08-25

Family

ID=78916065

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111155959.9A Active CN113821728B (en) 2021-09-29 2021-09-29 Content Recommendation Method and Device

Country Status (1)

Country Link
CN (1) CN113821728B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109977242A (en) * 2019-03-28 2019-07-05 北京奇艺世纪科技有限公司 A kind of recommended method, device, terminal device and computer readable storage medium
WO2019169963A1 (en) * 2018-03-07 2019-09-12 阿里巴巴集团控股有限公司 Content recommendation method, apparatus, electronic device, and system
CN111723289A (en) * 2020-06-08 2020-09-29 北京声智科技有限公司 Information recommendation method and device
CN111767466A (en) * 2020-09-01 2020-10-13 腾讯科技（深圳）有限公司 Recommendation information recommendation method and device based on artificial intelligence and electronic equipment
CN112052387A (en) * 2020-08-17 2020-12-08 腾讯科技（深圳）有限公司 Content recommendation method and device and computer readable storage medium
CN112307339A (en) * 2020-10-30 2021-02-02 中国平安人寿保险股份有限公司 User portrait based recommendation information generation method and device and computer equipment
CN113326442A (en) * 2020-11-17 2021-08-31 崔海燕 Recommended material pushing method and system based on big data positioning and cloud computing center

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019169963A1 (en) * 2018-03-07 2019-09-12 阿里巴巴集团控股有限公司 Content recommendation method, apparatus, electronic device, and system
CN109977242A (en) * 2019-03-28 2019-07-05 北京奇艺世纪科技有限公司 A kind of recommended method, device, terminal device and computer readable storage medium
CN111723289A (en) * 2020-06-08 2020-09-29 北京声智科技有限公司 Information recommendation method and device
CN112052387A (en) * 2020-08-17 2020-12-08 腾讯科技（深圳）有限公司 Content recommendation method and device and computer readable storage medium
CN111767466A (en) * 2020-09-01 2020-10-13 腾讯科技（深圳）有限公司 Recommendation information recommendation method and device based on artificial intelligence and electronic equipment
CN112307339A (en) * 2020-10-30 2021-02-02 中国平安人寿保险股份有限公司 User portrait based recommendation information generation method and device and computer equipment
CN113326442A (en) * 2020-11-17 2021-08-31 崔海燕 Recommended material pushing method and system based on big data positioning and cloud computing center

Also Published As

Publication number Publication date
CN113821728A (en) 2021-12-21

Similar Documents

Publication Publication Date Title
CN110909222B (en) User portrait establishing method and device based on clustering, medium and electronic equipment
CN109447713A (en) A kind of recommended method and device of knowledge based map
CN109471978B (en) Electronic resource recommendation method and device
US9459863B2 (en) System for assessing an application for tablet compatibility and quality
EP3451271A1 (en) Systems and methods for expediting rule-based data processing
CN110502357A (en) A kind of stack retrogressive method, device, medium and equipment
US20170364802A1 (en) System, method, and recording medium for expert recommendation while composing messages
CN113592535B (en) Advertisement recommendation method and device, electronic equipment and storage medium
CN110838041B (en) Virtual resource activity processing method and device, computer equipment and storage medium
CN115146146A (en) Information display method and device, terminal equipment and storage medium
CN113343109A (en) List recommendation method, computing device and computer storage medium
CN113434063A (en) Information display method, device and equipment
US20180129664A1 (en) System and method to recommend a bundle of items based on item/user tagging and co-install graph
CN113821728B (en) Content Recommendation Method and Device
CN110351581A (en) A kind of data request processing method, apparatus, terminal device and storage medium
CN115983902A (en) Information pushing method and system based on user real-time event
CN113761379B (en) Commodity recommendation method and device, electronic equipment and medium
CN110808899B (en) Content sharing method, device, client, server and system
CN111831179B (en) Signing method, device and computer readable medium
CN113705184A (en) Method and device for generating custom report, storage medium and electronic equipment
CN114357293A (en) Object recommendation method and device, electronic equipment and computer-readable storage medium
CN114780847A (en) Object information processing and information pushing method, device and system
CN113961797A (en) Resource recommendation method and device, electronic equipment and readable storage medium
CN113326680A (en) Method and device for generating table
CN109376294A (en) User interest point Weight Determination and device, storage medium and electronic equipment

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant